Related papers: Human-Imitating Metrics for Training and Evaluatin…

Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather posit privacy at a group level, a setting we call integral…

Alignment is a key step in developing Large Language Models (LLMs) using human feedback to ensure adherence to human values and societal norms. Dependence on human feedback raises privacy concerns about how much a labeler's preferences may…

The extensive use of online social media has highlighted the importance of privacy in the digital space. As more scientists analyse the data created in these platforms, privacy concerns have extended to data usage within the academia.…

Large Language Models (LLMs) are widely used in sensitive domains, including healthcare, finance, and legal services, raising concerns about potential private information leaks during inference. Privacy extraction attacks, such as…

Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are crucial to meet memory and inference time requirements, as…

Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally…

Machine learning (ML) models, demonstrably powerful, suffer from a lack of interpretability. The absence of transparency, often referred to as the black box nature of ML models, undermines trust and urges the need for efforts to enhance…

As opaque decision systems are being increasingly adopted in almost any application field, issues about their lack of transparency and human readability are a concrete concern for end-users. Amongst existing proposals to associate…

Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need…

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Human-like personality traits have recently been discovered in large language models, raising the hypothesis that their (known and as yet undiscovered) biases conform with human latent psychological constructs. While large conversational…

Today, computer systems hold large amounts of personal data. Yet while such an abundance of data allows breakthroughs in artificial intelligence, and especially machine learning (ML), its existence can be a threat to user privacy, and it…

In graph machine learning, data collection, sharing, and analysis often involve multiple parties, each of which may require varying levels of data security and privacy. To this end, preserving privacy is of great importance in protecting…

As social robots become increasingly prevalent in day-to-day environments, they will participate in conversations and appropriately manage the information shared with them. However, little is known about how robots might appropriately…

As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving…

With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the…

Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points. This raises the central question addressed in this…

Many modern statistical analysis and machine learning applications require training models on sensitive user data. Under a formal definition of privacy protection, differentially private algorithms inject calibrated noise into the…

Credit risk modeling has permeated our everyday life. Most banks and financial companies use this technique to model their clients' trustworthiness. While machine learning is increasingly used in this field, the resulting large-scale…

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…